Coexistence and local Mittag-Leffler stability of fractional-order recurrent neural networks with discontinuous activation functions Project supported by the Natural Science Foundation of Zhejiang Province, China (Grant Nos. LY18F030023, LY17F030016, and LY18F020028) and the National Natural Science Foundation of China (Grant Nos. 61503338, 61502422, and 61773348)

• Published in: Chinese physics B 2019-04, Vol.28 (4)
• Main Authors: Huang, Yu-Jiao, Chen, Shi-Jun, Yang, Xu-Hua, Xiao, Jie
• Format: Article
• Language: English
• Subjects: discontinuous activation function; fractional-order recurrent neural network; local Mittag-Leffler stability
• ISSN: 1674-1056
• DOI: 10.1088/1674-1056/28/4/040701

In this paper, coexistence and local Mittag-Leffler stability of fractional-order recurrent neural networks with discontinuous activation functions are addressed. Because of the discontinuity of the activation function, Filippov solution of the neural network is defined. Based on Brouwerʼs fixed point theorem and definition of Mittag-Leffler stability, sufficient criteria are established to ensure the existence of ( 2 k + 3 ) n ( k ≥ 1 ) equilibrium points, among which ( k + 2 ) n equilibrium points are locally Mittag-Leffler stable. Compared with the existing results, the derived results cover local Mittag-Leffler stability of both fractional-order and integral-order recurrent neural networks. Meanwhile discontinuous networks might have higher storage capacity than the continuous ones. Two numerical examples are elaborated to substantiate the effective of the theoretical results.